record_evidence

Persist normalized evidence sources, findings, limitations, and confidence.

Server Decision State MCP koolercat/mcp-state
Category Write
Risk class Medium
Parameters 00 required

What record_evidence does on Decision State MCP

AI agents use record_evidence to create or update resources in Decision State MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Decision State MCP environment.

Why record_evidence needs a policy

The tool writes/stores data (evidence, findings, limitations, confidence scores) to persistent state. This is a reversible write operation — it creates or updates records in the decision state store. No code execution, deletion, or financial operations are involved. Severity is low because misuse would only result in incorrect or misleading evidence records being stored, with limited blast radius.

From the tool's definition Persist normalized evidence sources, findings, limitations, and confidence.

Questions about record_evidence

What does the record_evidence tool do? +

Persist normalized evidence sources, findings, limitations, and confidence. It is categorised as a Write tool in the Decision State MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on record_evidence? +

Register the Decision State MCP server in PolicyLayer and add a rule for record_evidence: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Decision State MCP. Nothing to install.

What risk level is record_evidence? +

record_evidence is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit record_evidence? +

Yes. Add a rate_limit block to the record_evidence rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block record_evidence completely? +

Set action: deny in the PolicyLayer policy for record_evidence. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides record_evidence? +

record_evidence is provided by the Decision State MCP server (koolercat/mcp-state). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

record_evidence is one line of Decision State's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.